报告主题：Data-Driven Markov Decision Processes with Heterogeneous Groups: Regret Guarantees and Fairness Improvement via Robust Optimization
报告人简介：郑智超是新加坡管理大学运营管理副教授，研究方向为数据分析与优化，重点应用于医疗运营管理和临床决策支持，同时也涉及共享经济与供应链风险管理。他的研究成果发表在Operations Research、Management Science、Manufacturing & Service Operations Management等顶级期刊及多种医学期刊上，并担任Management Science、Service Science及Journal of Management Science and Engineering副主编。他亦多次受邀担任学术论文竞赛评审，尤其是医疗领域研究类竞赛。其研究获得新加坡教育部超过80万新元的竞争性科研资助。在教学方面，他在本科、硕士及MBA课程中讲授Management Science、Service and Operations Analytics、Data Analytics in Healthcare及Business Analytics课程。他于2009年获新加坡国立大学应用数学一等荣誉理学学士学位，并于2013年获管理学博士学位。
报告摘要：Healthcare datasets are often imbalanced and underrepresent certain demographic subgroups, such as those defined by ethnicity, gender, or region. This phenomenon, often described as data poverty, poses challenges for designing fair and effective policies, particularly in dynamic decision-making settings like patient interventions or resource allocation. We study this problem under a finite-horizon Markov Decision Process (MDP) framework where population groups differ in both transition dynamics and reward functions. We first establish a probabilistic regret bound and show that transition uncertainty dominates the performance gap for minority-group policies learned from limited data. To mitigate the impact of data poverty, we examine the effectiveness of pooling data across groups. While naïve pooling can exacerbate bias, we show that combining data pooling with distributionally robust optimization, using a type-1 Wasserstein ambiguity set, can yield substantial fairness and performance gains. In particular, we find that moderate robustness levels can reduce regret for minority groups without significantly degrading majority outcomes. Moreover, robustness within a certain threshold can monotonically improve collective performance, reinforcing its role as an uncertainty regularizer. More importantly, we show that robustness amplifies the fairness benefits of data pooling under severe data imbalance, effectively acting as a fairness regularizer. Numerical experiments on an ICU extubation task validate our theoretical findings, demonstrating that robust pooling improves both overall outcomes and fairness.
